CVE-2026-115921
Description
Open Neural Network Exchange (ONNX) is an open standard for machine learning interoperability. From 1.4.0 until 1.22.0, ScanInferenceFunction, ScanInferenceFunction_opset8, and ScanInferenceFunction_opset9 do not safely validate the required num_scan_inputs attribute. A missing attribute is dereferenced as a null pointer, while a negative value is converted to size_t and can reach an exceptional oversized allocation path. An untrusted model can therefore terminate or disrupt shape inference, including a negative-value model that can pass onnx.checker.check_model(). This issue is fixed in version 1.22.0.
How to fix
- onnx1.22.0 or later
Affected products
| Product | Affected versions | Fixed in |
|---|---|---|
| onnxPyPI | 1.4.0 ≤ v ≤ 1.21.0 | 1.22.0 |
| microsoft azl3_pytorch_2.2.2-17 | No range specified | — |
Check your version
Choose the product and enter the version you run to see whether it falls in the affected range.
Attack Surface Management
See the assets tied to your domains, the technologies they run and known vulnerabilities in one list.